Bases por anio

He unido los archivos de cada modulo para tener una sola base por anio. Algunas encuestas son dirigidas a la mujer en edad fertil/madre, otras nivel hogar. Como veran, solo la base de programas sociales es a nivel hogar (de las que he usado), por eso es la unica que el join es por HHID. Las demas, son dirigidas a la madre/MEF.

Gestantes 2020

gestacion1 <- read_sav("./data/raw/endes back up/2020/RE223132.sav")
gestacion2 <- read_sav("./data/raw/endes back up/2020/REC94.sav") # outcome # id
violence <- read_sav("./data/raw/endes back up/2020/REC84DV.sav")
sociodemo <- read_sav("./data/raw/endes back up/2020/REC0111.sav") %>% select(-NCONGLOME)
vih1 <- read_sav("./data/raw/endes back up/2020/RE758081.sav")
vih2 <- read_sav("./data/raw/endes back up/2020/REC91.sav")
programas <- read_sav("./data/raw/endes back up/2020/Programas Sociales x Hogar.sav") ## id


# Gestantes

df_gestantes2020<-
  gestacion2 %>% 
  left_join(gestacion1, by = "CASEID") %>% 
  left_join(violence, by = "CASEID") %>% 
  left_join(sociodemo, by = "CASEID") %>%
  left_join(vih1, by = "CASEID") %>% 
  left_join(vih2, by = "CASEID") %>%
  
  mutate(
    HHID = as.numeric(str_sub(CASEID,1,-3)),
    year = 2020
    
  ) %>% 
  left_join(programas %>% 
              mutate(
                HHID = as.numeric(HHID)),by = c("HHID"))

Gestantes 2019

gestacion1 <- read_sav("./data/raw/endes back up/2019/RE223132.sav")
gestacion2 <- read_sav("./data/raw/endes back up/2019/REC94.sav") # outcome # id
violence <- read_sav("./data/raw/endes back up/2019/REC84DV.sav")
sociodemo <- read_sav("./data/raw/endes back up/2019/REC0111.sav")
vih1 <- read_sav("./data/raw/endes back up/2019/RE758081.sav")
vih2 <- read_sav("./data/raw/endes back up/2019/REC91.sav")
programas <- read_sav("./data/raw/endes back up/2019/Programas Sociales x Hogar.sav") ## id


# Gestantes

df_gestantes2019<-
  gestacion2 %>% 
  left_join(gestacion1, by = "CASEID") %>% 
  left_join(violence, by = "CASEID") %>% 
  left_join(sociodemo, by = "CASEID") %>%
  left_join(vih1, by = "CASEID") %>% 
  left_join(vih2, by = "CASEID") %>%
  
  mutate(
    HHID = as.numeric(str_sub(CASEID,1,-3)),
    year = 2019
    
  ) %>% 
  left_join(programas %>% 
              mutate(
                HHID = as.numeric(HHID)),by = c("HHID"))

Gestantes 2018

gestacion1 <- read_sav("./data/raw/endes back up/2018/RE223132.sav")
gestacion2 <- read_sav("./data/raw/endes back up/2018/REC94.sav") # outcome # id
violence <- read_sav("./data/raw/endes back up/2018/REC84DV.sav")
sociodemo <- read_sav("./data/raw/endes back up/2018/REC0111.sav")
vih1 <- read_sav("./data/raw/endes back up/2018/RE758081.sav")
vih2 <- read_sav("./data/raw/endes back up/2018/REC91.sav")
programas <- read_sav("./data/raw/endes back up/2018/Programas Sociales x Hogar.sav") ## id


# Gestantes

df_gestantes2018<-
  gestacion2 %>% 
  left_join(gestacion1, by = "CASEID") %>% 
  left_join(violence, by = "CASEID") %>% 
  left_join(sociodemo, by = "CASEID") %>%
  left_join(vih1, by = "CASEID") %>% 
  left_join(vih2, by = "CASEID") %>%
  
  mutate(
    HHID = as.numeric(str_sub(CASEID,1,-3)),
    year = 2018
    
  ) %>% 
  left_join(programas %>% 
              mutate(
                HHID = as.numeric(HHID)),by = c("HHID"))

Gestantes 2017

gestacion1 <- read_sav("./data/raw/endes back up/2017/RE223132.sav")
gestacion2 <- read_sav("./data/raw/endes back up/2017/REC94.sav") # outcome # id
violence <- read_sav("./data/raw/endes back up/2017/REC84DV.sav")
sociodemo <- read_sav("./data/raw/endes back up/2017/REC0111.sav")
vih1 <- read_sav("./data/raw/endes back up/2017/RE758081.sav")
vih2 <- read_sav("./data/raw/endes back up/2017/REC91.sav")
programas <- read_sav("./data/raw/endes back up/2017/Programas Sociales x Hogar.sav") ## id


# Gestantes

df_gestantes2017<-
  gestacion2 %>% 
  left_join(gestacion1, by = "CASEID") %>% 
  left_join(violence, by = "CASEID") %>% 
  left_join(sociodemo, by = "CASEID") %>%
  left_join(vih1, by = "CASEID") %>% 
  left_join(vih2, by = "CASEID") %>%
  
  mutate(
    HHID = as.numeric(str_sub(CASEID,1,-3)),
    year = 2017
    
  ) %>% 
  left_join(programas %>% 
              mutate(
                HHID = as.numeric(HHID)),by = c("HHID"))

Gestantes 2016

gestacion1 <- read_sav("./data/raw/endes back up/2016/RE223132.sav")
gestacion2 <- read_sav("./data/raw/endes back up/2016/REC94.sav") # outcome # id
violence <- read_sav("./data/raw/endes back up/2016/REC84DV.sav")
sociodemo <- read_sav("./data/raw/endes back up/2016/REC0111.sav")
vih1 <- read_sav("./data/raw/endes back up/2016/RE758081.sav")
vih2 <- read_sav("./data/raw/endes back up/2016/REC91.sav")
programas <- read_sav("./data/raw/endes back up/2016/Programas Sociales x Hogar.sav") ## id


# Gestantes

df_gestantes2016<-
  gestacion2 %>% 
  left_join(gestacion1, by = "CASEID") %>% 
  left_join(violence, by = "CASEID") %>% 
  left_join(sociodemo, by = "CASEID") %>%
  left_join(vih1, by = "CASEID") %>% 
  left_join(vih2, by = "CASEID") %>%
  
  mutate(
    HHID = as.numeric(str_sub(CASEID,1,-3)),
    year = 2016
    
  ) %>% 
  left_join(programas %>% 
              mutate(
                HHID = as.numeric(HHID)),by = c("HHID"))

Gestantes 2015

gestacion1 <- read_sav("./data/raw/endes back up/2015/RE223132.sav")
gestacion2 <- read_sav("./data/raw/endes back up/2015/REC94.sav") # outcome # id
violence <- read_sav("./data/raw/endes back up/2015/REC84DV.sav")
sociodemo <- read_sav("./data/raw/endes back up/2015/REC0111.sav")
vih1 <- read_sav("./data/raw/endes back up/2015/RE758081.sav")
vih2 <- read_sav("./data/raw/endes back up/2015/REC91.sav")
programas <- read_sav("./data/raw/endes back up/2015/Programas Sociales x Hogar.sav") ## id


# Gestantes

df_gestantes2015<-
  gestacion2 %>% 
  left_join(gestacion1, by = "CASEID") %>% 
  left_join(violence, by = "CASEID") %>% 
  left_join(sociodemo, by = "CASEID") %>%
  left_join(vih1, by = "CASEID") %>% 
  left_join(vih2, by = "CASEID") %>%
  
  mutate(
    HHID = as.numeric(str_sub(CASEID,1,-3)),
    year = 2015
    
  ) %>% 
  left_join(programas %>% 
              mutate(
                HHID = as.numeric(HHID)),by = c("HHID"))

Union de bases

Hasta aqui ya esta cada base por cada anio generada. Lo que sigue es unir las bases (cada una tiene una variable “year” que indica el anio). Lo que he hecho es unir de dos en dos y luego agruparlas. Deberia poder hacerse defrente de las 6 con bind_rows pero no se porque no me funciona. Lo revisare luego. Igual, posiblemente hagamos un paso extra mas si creamos una funcion para seleccionar/crear las variables que vayamos a utilizar para el analisis. Cuando nos reunamos les ensenio que hice con el proyecto de vacunas.

df<- bind_rows(df_gestantes2015,df_gestantes2016)
df2<- bind_rows(df_gestantes2017,df_gestantes2018)
df3<- bind_rows(df_gestantes2019,df_gestantes2020)

dataset2<-bind_rows(df,df2,df3)

Datos

Muestra gratis :v de la data general de los 5 anios (Solo he seleccionado variables al azar). Como les comentaba arriba, deberia haber un paso mas que seria seleccionar y crear/modifcar las variables que vamos a necesitar. Eso lo podemos hacer mediante una funcion y con un purrr::map_df seria todo. Revisen el codigo y si algo no les parece nos avisan :D

dataset2 %>% 
  select(S411H,year,SREGION,V005,V001,V022) %>% 
  DT::datatable()

## Warning in instance$preRenderHook(instance): It seems your data is too big
## for client-side DataTables. You may consider server-side processing: https://
## rstudio.github.io/DT/server.html

Gestantes_vih

JoseM

2/01/2022